Small Object Detection Based on Modified FSSD and Model Compression

• URL: http://arxiv.org/abs/2108.10503v1
• Date: Tue, 24 Aug 2021 03:20:32 GMT
• Title: Small Object Detection Based on Modified FSSD and Model Compression
• Authors: Qingcai Wang, Hao Zhang, Xianggong Hong, and Qinqin Zhou
• Abstract summary: This paper proposes a small object detection algorithm based on FSSD. In order to reduce the computational cost and storage space, pruning is carried out to achieve model compression. The average accuracy (mAP) of the algorithm can reach 80.4% on PASCAL VOC and the speed is 59.5 FPS on GTX1080ti.
• Score: 7.387639662781843
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small objects have relatively low resolution, the unobvious visual features which are difficult to be extracted, so the existing object detection methods cannot effectively detect small objects, and the detection speed and stability are poor. Thus, this paper proposes a small object detection algorithm based on FSSD, meanwhile, in order to reduce the computational cost and storage space, pruning is carried out to achieve model compression. Firstly, the semantic information contained in the features of different layers can be used to detect different scale objects, and the feature fusion method is improved to obtain more information beneficial to small objects; secondly, batch normalization layer is introduced to accelerate the training of neural network and make the model sparse; finally, the model is pruned by scaling factor to get the corresponding compressed model. The experimental results show that the average accuracy (mAP) of the algorithm can reach 80.4% on PASCAL VOC and the speed is 59.5 FPS on GTX1080ti. After pruning, the compressed model can reach 79.9% mAP, and 79.5 FPS in detection speed. On MS COCO, the best detection accuracy (APs) is 12.1%, and the overall detection accuracy is 49.8% AP when IoU is 0.5. The algorithm can not only improve the detection accuracy of small objects, but also greatly improves the detection speed, which reaches a balance between speed and accuracy.

Related papers

• ESOD: Efficient Small Object Detection on High-Resolution Images [36.80623357577051]
  Small objects are usually sparsely distributed and locally clustered. Massive feature extraction computations are wasted on the non-target background area of images. We propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing.
  arXiv  Detail & Related papers  (2024-07-23T12:21:23Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• Patch-based Selection and Refinement for Early Object Detection [20.838511460733038]
  We propose a novel set of algorithms that divide the image into patches, select patches with objects at various scales, elaborate the details of a small object, and detect it as early as possible. Our approach is built upon a transformer-based network and integrates the diffusion model to improve the detection accuracy. Our algorithms enhance the mAP for small objects from 1.03 to 8.93, and reduce the data volume in computation by more than 77%.
  arXiv  Detail & Related papers  (2023-11-03T23:41:13Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• Fewer is More: Efficient Object Detection in Large Aerial Images [59.683235514193505]
  This paper presents an Objectness Activation Network (OAN) to help detectors focus on fewer patches but achieve more efficient inference and more accurate results. Using OAN, all five detectors acquire more than 30.0% speed-up on three large-scale aerial image datasets. We extend our OAN to driving-scene object detection and 4K video object detection, boosting the detection speed by 112.1% and 75.0%, respectively.
  arXiv  Detail & Related papers  (2022-12-26T12:49:47Z)
• Optimizing ship detection efficiency in SAR images [12.829941550630776]
  The speed and compute cost of vessel detection are essential for a timely intervention to prevent illegal fishing. We trained an object detection model based on a convolutional neural network (CNN) using a dataset of satellite images. We show that by using a classification model the average precision of the detection model can be approximated to 99.5% in 44% of the time or to 92.7% in 25% of the time.
  arXiv  Detail & Related papers  (2022-12-12T12:04:10Z)
• EAutoDet: Efficient Architecture Search for Object Detection [110.99532343155073]
  EAutoDet framework can discover practical backbone and FPN architectures for object detection in 1.4 GPU-days. We propose a kernel reusing technique by sharing the weights of candidate operations on one edge and consolidating them into one convolution. In particular, the discovered architectures surpass state-of-the-art object detection NAS methods and achieve 40.1 mAP with 120 FPS and 49.2 mAP with 41.3 FPS on COCO test-dev set.
  arXiv  Detail & Related papers  (2022-03-21T05:56:12Z)
• Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation [79.78017059539526]
  We propose a new heatmap-free keypoint estimation method in which individual keypoints and sets of spatially related keypoints (i.e., poses) are modeled as objects within a dense single-stage anchor-based detection framework. In experiments, we observe that KAPAO is significantly faster and more accurate than previous methods, which suffer greatly from heatmap post-processing. Our large model, KAPAO-L, achieves an AP of 70.6 on the Microsoft COCO Keypoints validation set without test-time augmentation.
  arXiv  Detail & Related papers  (2021-11-16T15:36:44Z)
• PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices [13.62426382827205]
  PP-PicoDet family of real-time object detectors achieves superior performance on object detection for mobile devices. Models achieve better trade-offs between accuracy and latency compared to other popular models.
  arXiv  Detail & Related papers  (2021-11-01T12:53:17Z)
• You Better Look Twice: a new perspective for designing accurate detectors with reduced computations [56.34005280792013]
  BLT-net is a new low-computation two-stage object detection architecture. It reduces computations by separating objects from background using a very lite first-stage. Resulting image proposals are then processed in the second-stage by a highly accurate model.
  arXiv  Detail & Related papers  (2021-07-21T12:39:51Z)
• FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving [0.0]
  We propose a lightweight one-stage object detector that is balanced to satisfy all the constraints of accuracy, model size, and real-time processing. Our network aims to maximize the compression of the model while achieving or surpassing YOLOv3 level of accuracy.
  arXiv  Detail & Related papers  (2020-11-16T16:15:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.